Objectives of this study - (I made this report with dummy data.)

The mental health of university students is an area of increasing concern worldwide. Although some recent studies revealed a high prevalence of depression and anxiety among Bangladeshi university students, no study has yet investigated the link between marriage pressure and these common psychological disorders and their effects on career and goal setup. Therefore, aims of these study is-

  • To determine the state of marriage pressure on female undergraduate students -To determine the association between mental health and marriage pressure.
  • To determine how marriage pressure affects education, career, and goal setup.
  • To determine the influencing factors behind marriage pressure

Descriptive Statistics - Frequency analysis

library(readxl)
data <- read_excel("F:/Fiverr/up-work project/dataset/project 68.xlsx")
tbl<- knitr::kable(table(data$MarriagePressure),col.names = c("Marriage Pressure", "Count"), "simple")
tbl
Marriage Pressure Count
no 587
yes 349 
library(plotly)
fig <- plot_ly(data, labels = ~MarriagePressure, values = ~frequency(MarriagePressure), type = 'pie')

fig <- fig %>% layout(title = 'Marriage Pressure of Female Students',
                      
                      xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
                      
                      yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
                      width = "50%", 
                      height = 450)

fig

A total of 936 participants responded to the survey. Of these, 587 participants answered “No” to the question about having marriage pressure, while 349 participants answered “Yes.”

The results of the survey indicate that the majority of participants 62.7% answered “No” to the question about having marriage pressure. Only 37.3% participants answered “Yes.” This data suggests that a larger proportion of the participants did not experience marriage pressure, while a smaller proportion reported that they did. The pie chart provides a clear and straightforward representation of the distribution of responses and highlights the differences between the two categories.

When we look after another variable PHQ-9 (Patient Health Question) the scores were then analyzed to categorize the students into different levels of depression severity, including normal depression, mild depression, moderate depression, moderately severe depression, and severe depression.

Depression Severity among students

phq_categories<- ifelse(data$phq9 <= 4, "Normal",
       ifelse(data$phq9 <= 9, "Mild", 
              ifelse(data$phq9 <= 14,"Moderate",
                     ifelse(data$phq9 <= 19, "Moderately Severe", 
                            ifelse(data$phq9 <=27,"Severe",data$phq9)))))


phq_categories <- table(phq_categories)
phq_categories_df <- as.data.frame(phq_categories, stringsAsFactors = FALSE)
colnames(phq_categories_df) <- c("Depression Severity", "Frequency")
knitr::kable(phq_categories_df, col.names = c("Depression Severity", "Frequency"), "simple")
Depression Severity Frequency
Mild 248
Moderate 224
Moderately Severe 136
Normal 272
Severe 56 
library(plotly)
fig <- plot_ly(phq_categories_df, x = ~`Depression Severity`, y = ~Frequency, type = "bar", color = ~`Depression Severity`) %>% 
  layout(title = "Depression Severity Categories", xaxis = list(title = "Category"), yaxis = list(title = "Frequency"))

fig

Marriage Pressure determining by Academic Year

tt<-rbind(
  
  
  nrow(data[data$Year == '1st' & data$MarriagePressure == 'yes', ]),
  nrow(data[data$Year == '2nd' & data$MarriagePressure == 'yes', ]),
  nrow(data[data$Year == '3rd' & data$MarriagePressure == 'yes', ]),
  nrow(data[data$Year == '4th' & data$MarriagePressure == 'yes' , ]),
  nrow(data[data$Year == 'masters' & data$MarriagePressure == 'yes', ])
)

academic_yr <- matrix(c('1st','2nd','3rd','4th','masters'), ncol=1)

table_aca<- cbind(academic_yr,tt)

table_aca_df <- as.data.frame(table_aca, stringsAsFactors = FALSE)

# Rename the columns
colnames(table_aca_df) <- c("Academic Year", "Marriage Pressure(yes)")


total_stu<- data.frame(table(data$Year))
colnames(total_stu) <- c("Academic Year", "Marriage Pressure(yes)")

# Merge the two data frames by the "Academic Year" column
merged_df <- merge(table_aca_df, total_stu, by = 'Academic Year' )

knitr::kable(merged_df, col.names = c("Academic Year", "Marriage pressure(yes)", "Total Student"), "simple")
Academic Year Marriage pressure(yes) Total Student
1st 141 215
2nd 27 227
3rd 78 350
4th 80 96
masters 23 48

The given survey data contains information about the academic year, marriage pressure, and total number of students. Using this data, we created a frequency table and a clustered bar chart to visualize the relationship between academic year, marriage pressure, and total number of students. We also created an interactive stacked bar chart to allow for further exploration of the data.

# Create the bar chart
library(plotly)

plot_ly(merged_df, x = ~merged_df$`Academic Year`, y = ~`Marriage Pressure(yes).x`, name = "Marriage Pressure",
        type = "bar", marker = list(color = "#F8766D")) %>%
  add_trace(y = ~`Marriage Pressure(yes).y`, name = "Total Students",
            marker = list(color = "#00BFC4")) %>%
  layout(title = "Marriage Pressure vs Total Students by Academic Year",
         xaxis = list(title = "Academic Year"),
         yaxis = list(title = "Frequency"),
         barmode = "stack")

Overall, the analysis suggests that marriage pressure may have an impact on the academic decisions of students, with higher levels of marriage pressure being associated with fewer students in higher academic years.

To determine the association between mental health and marriage pressure.

library(dplyr)
df<- data %>%
  select(phq9) %>%
  mutate(phqcat = 
           ifelse(phq9 <= 4, 1,
                  ifelse(phq9 <= 9,2,
                         ifelse(phq9<= 14,3,
                                ifelse(phq9<= 19,4,
                                       ifelse(phq9<= 27, 5, data$phq9)))))
           )

data<- merge(data, df, by = 'phq9')

library(kableExtra)

# Execute Pearson's Chi-squared test
result <- chisq.test(data$MarriagePressure, data$phqcat)

# Create a table with the results
tbl <- data.frame(
  "Test" = "Pearson's Chi-squared test",
  "Variables" = "Marriage Pressure and phq9 Categories",
  "X-squared" = round(result$statistic, 2),
  "df" = result$parameter,
  "p-value" = format.pval(result$p.value)
) %>%
  kable(align = "c") %>%
  kable_styling(full_width = FALSE)

# Print the table
tbl
Test Variables X.squared df p.value
X-squared Pearson’s Chi-squared test Marriage Pressure and phq9 Categories 272.24 4 < 2.22e-16